Multiplier • Termination Agent • 2025
Making separation cases compliant and self serve for HR admins through AI.
The Problem
Complex, multi-regional employee terminations were handled through scattered Zendesk tickets and heavy manual Ops dependencies, creating bottlenecks and severe legal compliance risks.
The Solution
Designed a 0-to-1, self-serve AI Separation Agent that automatically extracts contract data, enforces regional labor laws (like the Philippine Two-Notice Rule), and guides HR Admins through a compliant step-by-step workflow
The Impact
Reduced termination-related Zendesk tickets by an estimated 75% and significantly decreased HR Ops dependency by enabling fully self-serve, legally defensible termination cases (metrics as per beta testing phase) .
My Role
Product Designer (0 to 1) – Owned the end-to-end UX/UI, AI conversation design, and compliance mapping, collaborating directly with Product and Engineering to define the core experience.
Core Problem Statement
Global HR Admins need a way to independently execute complex, multi-regional employee separations because navigating localised labor laws—or statutory redundancy payouts—requires deep legal expertise they typically lack, but currently they must rely on manual, scattered back-and-forth communication through Zendesk with Ops and Legal teams, causing severe bottlenecks and compliance risks.
Business Context
The Operational Bottleneck
Separations were historically buried in scattered Zendesk tickets. By productizing legal expertise into the Separation Command Center, we eliminated the 24–48 hour wait times for manual Ops support on global compliance questions.
The Legal & Financial Risk
Mishandling procedural due process—like the 5-day NTE rule in the Philippines—exposes the company to severe litigation. I designed the system to enforce these guardrails automatically, preventing illegal dismissal claims before they happen.
The Business Incentive
To scale global EOR services, the business needed to reduce OpEx. The AI Agent automates high-touch advisory tasks, protecting company margins while providing a unified, auditable, and risk-mitigated offboarding experience.
Technical Constraint: AI Parsing vs. Legal Reliability
The Ideal
AI instantly ingests any contract, maps local laws, and executes the termination.
The Reality
Contracts are often messy, scanned PDFs. Blindly relying on AI extraction posed a massive legal risk.
The Adaptation
I designed mandatory "Data Validation" screens. The AI pre-fills data (Start Dates, Probation Periods), but the HR Admin must review and edit before any legal notices are generated.
Showcases the user dropping a PDF contract → AI parsing state → "Quick Details" view. The zoom-in on the Edit Button emphasizes the human-in-the-loop requirement.
Compliance Constraint: The "Human-in-the-Loop" Requirement
The Ideal
A touchless, fully automated separation process.
The Reality
High-risk markets (like the Philippines) require strict procedural due process (e.g., the Two-Notice Rule). AI cannot assess emotional volatility or nuanced retaliation risks.
The Adaptation
The system acts as a "Copilot," not an "Autopilot." I integrated Escalation Triggers that pause automation if a case involves protected categories or weak documentation.
The HR Admin types "I’ve had enough, just terminate." The Chatbot triggers a "Hard Stop" warning, preventing a legally risky rush.
The "Dynamic Checklist + Chat" Hybrid
What I Did
Paired a vertical compliance checklist with a conversational stage.
The Trade-off
We traded the simplicity of a standard wizard for Adaptive Flexibility.
The Admin mentions the employee has absconded. The side panel dynamically re-routes the checklist from PIP steps to AWOL steps in real-time.
Persistent Inputs & Structured Quick Actions
What I Did
While the prompt remains open for nuance, the AI proactively suggests Quick Action Buttons to keep the workflow on track.
The Trade-off
Traded strict UI constraints for User Freedom, ensuring critical legal context isn't lost.
As the bot replies, contextual buttons pop up (e.g., "Schedule Hearing" or "Upload PIP"). This keeps the user within the "happy path" of the legal workflow.
Strategic Risk Mitigation (MSA over Termination)
What I Did
The AI is architected to pitch a Mutual Separation Agreement (MSA) as the primary path, even if the user asks for formal termination.
The Trade-off
In many jurisdictions, formal terminations are high-risk. MSAs mitigate litigation risk. Traded immediate severance cost for Long-term Legal Protection.
The Agent captures the intent, identifies legal risk, and the canvas zooms in on the "Mutual Separation" recommendation card.
Full-Cycle Integration: Beyond the Chat
To make the tool truly "End-to-End," I integrated the administrative heavy lifting directly into the interface.
Meeting Scheduling & Summarization
Instead of jumping to Zoom or Outlook, the Agent handles the "Administrative Hearing" directly.
Admin clicks "Schedule" → Calendar opens → Email sent. Post-call, the AI summarizes the meeting and pre-populates the next legal step.
In-Built Communication Hub
To maintain a legally defensible audit trail, all communications happen within the tool.
The AI drafts the formal notice based on the case history. The user reviews, edits, and sends it directly through the chat interface.
Impact & Business Results
From Operational Bottleneck to "Separation Command Center"
By transitioning from scattered Zendesk tickets and manual email threads to a unified AI Copilot, we transformed the HR Ops workflow:
75% Reduction in Zendesk Tickets
R Admins can now self-serve complex legal procedures. We eliminated the 24-48 hour wait time for Ops or Legal teams to manually explain local labor laws.
100% Procedural Compliance
By enforcing "Hard Stop" guardrails—such as the mandatory 5-day Notice to Explain (NTE) window in the Philippines—we effectively eliminated procedural errors that previously exposed the company to illegal dismissal claims.
Drastic Time-to-Notice Reduction:
Reduced manual processing from 4–6 hours of fragmented coordination to a 20-minute AI-guided workflow for fully compliant separation packages.
Strategic Risk Mitigation
The AI calculates litigation exposure in real-time, intelligently prioritizing Mutual Separation Agreements (MSAs) over hostile terminations to protect the company’s bottom line.
Designed with love by Rishikesh
